Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    phrases indicating the presence or absence of certain conditions or situations

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating the presence or absence of situations or conditions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Sins
    -0.78
    stars
    -0.75
     Seasons
    -0.74
     Industries
    -0.73
    jas
    -0.72
     charms
    -0.71
    olor
    -0.70
    isms
    -0.69
     Characters
    -0.69
    isites
    -0.68
    POSITIVE LOGITS
     insufficient
    1.11
     no
    1.10
     disagreement
    1.05
     ample
    1.05
     nothing
    0.91
     sufficient
    0.91
     evidence
    0.89
     overlap
    0.88
     speculation
    0.88
     uncertainty
    0.87
    Act Density 0.135%

    No Known Activations